Skip to content

seastar105

audio-lfm2.5-1.2b-wavcaps-paraspeech-20k

seastar105/audio-lfm2.5-1.2b-wavcaps-paraspeech-20k

audio-lfm2.5-1.2b-wavcaps-paraspeech-20k is a audio-text-to-text model from seastar105. Use it for the audio-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for vllm. The card lists the license as other.

This repository contains the 20,000-update projector export from the Audio LFM experiment. It joins a frozen openai/whisper-small encoder to a frozen LiquidAI/LFM2.5-1.2B-Instruct decoder using a trainable 4x temporal…

Downloads · 30 days

16

17% of all-time downloads

All-time downloads

96

Public

Parameters

10.5M

42 MB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors42 MB · 90%

At a glance

Task
Audio-Text-to-Text
Library
vllm
License
other
Model type
lfm2
Access
Public
Created
Aug 26, 2026
Updated
Aug 26, 2026
SHA
65879c5d

Base models

Task
Audio-Text-to-Text
Library
vllm
Type
lfm2
License
other
Languages
en, ko, ja
Created
Aug 26, 2026
Updated
Aug 26, 2026